A data center GPU against a workstation card, one Ada Lovelace and one Blackwell: 48 GB GDDR6 against 96 GB GDDR7 and 85% more memory bandwidth on the RTX PRO 6000.
At a glance
Memory
- L40
- 48 GB
- RTX PRO 6000
- 96 GB
2x more on RTX PRO 6000
Memory bandwidth
- L40
- 864 GB/s
- RTX PRO 6000
- 1,597 GB/s
1.8x higher on RTX PRO 6000
Cheapest on-demand
- L40
- $0.78 /GPU/hr
- RTX PRO 6000
- $0.66 /GPU/hr
15% cheaper on RTX PRO 6000
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | L40 | RTX PRO 6000 | Difference |
|---|---|---|---|
| On-demand | $1.05 /GPU/hr from $0.78 | $2.21 /GPU/hr from $0.66 | 2.1x more expensive on RTX PRO 6000 |
| Reserved | -- /GPU/hr from $0.70 | $1.81 /GPU/hr from $0.48 (1 mo) | |
| Spot | $0.79 /GPU/hr from $0.77 | $1.29 /GPU/hr from $0.94 | 39% cheaper on L40 |
Heads up: A provider's own page may quote a different figure, for example on tax, region or a promotion. A monthly-only plan shows a derived hourly rate. Medians are across providers, one vote each, so a large catalog does not outweigh a small one. No median for reserved on the L40: we only show one when at least 3 providers list the GPU on that billing type. Verify before provisioning. More on how we price.
Price history
L40 vs RTX PRO 6000 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | L40 | RTX PRO 6000 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 48 GB GDDR6 | 96 GB GDDR7 | 2x more on RTX PRO 6000 |
| Bandwidth | 864 GB/s | 1,597 GB/s | 1.8x higher on RTX PRO 6000 |
| Bus width | 384-bit | 512-bit | 1.3x wider on RTX PRO 6000 |
| Compute · dense | |||
| FP4 | Not supported | 2,000 TFLOPS | RTX PRO 6000 only |
| FP8 | 362 TFLOPS | 1,000 TFLOPS | 2.8x higher on RTX PRO 6000 |
| FP16 / BF16 | 181.1 TFLOPS | 500 TFLOPS | 2.8x higher on RTX PRO 6000 |
| INT8 | 362 TOPS | 1,000 TOPS | 2.8x higher on RTX PRO 6000 |
| FP32 | 90.5 TFLOPS | 120 TFLOPS | 1.3x higher on RTX PRO 6000 |
| Platform | |||
| Interconnect | PCIe only | PCIe only | |
| Board power | 300 W | 600 W | 2x higher on RTX PRO 6000 |
| Released | Q4 2022 | Q1 2025 | 2 years newer on RTX PRO 6000 |
| Precision | |||
| Supported formats | FP8FP16BF16TF32FP32INT4INT8 | FP4FP8FP16BF16TF32FP32INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: L40 datasheet and RTX PRO 6000 datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | L40 /GPU/hr | RTX PRO 6000 /GPU/hr |
|---|---|---|
GPU.ai
|
On-Demand $0.78 | On-Demand $1.99 |
Thunder Compute
|
On-Demand $0.79 | -- |
Massed Compute
|
On-Demand $0.86 | -- |
Sesterce
|
On-Demand $0.97 | -- |
Runcrate
|
On-Demand $0.97 | -- |
Oblivus
|
On-Demand $1.05 | -- |
Spheron
|
On-Demand $1.06 | -- |
EmpirioLabs AI
|
On-Demand $1.50 | -- |
Packet·ai
|
-- | On-Demand $0.66 |
HyperAI
|
-- | On-Demand $0.80 |
GPUhub
|
-- | On-Demand $1.10 |
EcoHash
|
-- | On-Demand $1.89 |
Verda
|
-- | On-Demand $1.89 |
Cloudzy
|
-- | On-Demand $1.93 |
Runpod
|
-- | On-Demand $2.09 |
12 providers list the L40 and 44 the RTX PRO 6000. Every listing is on the L40 page and the RTX PRO 6000 page.
Similar GPUs
Other comparisons in the same class.
Our data for Nvidia L40 was last updated on Sept. 7, 2026, and for Nvidia RTX PRO 6000 on Sept. 7, 2026.